Answers are grounded in this paper and cite their sources.
Demonstrates methods for setting acceptance limits considering measurement uncertainty and risk in various distributions, highlighting practical applications.
Document JCGM 106:2012, encompassed in the ISO-IEC Guide 98-4, provides guidelines for comparing a measurement result with a tolerance interval, considering that, according to the Guide to the Expression of Uncertainty in Measurement (GUM), a measurement result is not a single value but rather a distribution of values. Therefore, the comparison does not always lead to a fully certain decision. In fact, when the distribution crosses the tolerance limits, there is a risk of making an incorrect decision. JCGM 106:2012 offers general recommendations about setting acceptance or rejection limits, without providing details on how to compute them under practical situations. This paper addresses most practical situations, considering cases of normal and non-normal distributions and cases where the distribution of values that can be reasonably be attributed to the measurand are obtained through Monte Carlo simulations. Additionally, it allows for considering any desired level of decision risk, which can be set based on the specific situation or application.
No takes yet. Share an insight, caveat, or question.
Ferrero et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: